FuseCap: Leveraging Large Language Models to Fuse Visual Data into Enriched Image Captions

Image captioning is a central task in computer vision which has experienced substantial progress following the advent of vision-language pre-training techniques. In this paper, we highlight a frequently overlooked limitation of captioning models that often fail to capture semantically significant elements. This drawback can be traced back to the text-image datasets; while their captions typically offer a general depiction of image content, they frequently omit salient details. To mitigate this limitation, we propose FuseCap - a novel method for enriching captions with additional visual information, obtained from vision experts, such as object detectors, attribute recognizers, and Optical Character Recognizers (OCR). Our approach fuses the outputs of such vision experts with the original caption using a large language model (LLM), yielding enriched captions that present a comprehensive image description. We validate the effectiveness of the proposed caption enrichment method through both quantitative and qualitative analysis. Our method is then used to curate the training set of a captioning model based BLIP which surpasses current state-of-the-art approaches in generating accurate and detailed captions while using significantly fewer parameters and training data. As additional contributions, we provide a dataset comprising of 12M image-enriched caption pairs and show that the proposed method largely improves image-text retrieval.

Learning Differential Invariants of Planar Curves

We propose a learning paradigm for the numerical approximation of differential invariants of planar curves. Deep neural-networks' (DNNs) universal approximation properties are utilized to estimate geometric measures. The proposed framework is shown to be a preferable alternative to axiomatic constructions. Specifically, we show that DNNs can learn to overcome instabilities and sampling artifacts and produce consistent signatures for curves subject to a given group of transformations in the plane. We compare the proposed schemes to alternative state-of-the-art axiomatic constructions of differential invariants. We evaluate our models qualitatively and quantitatively and propose a benchmark dataset to evaluate approximation models of differential invariants of planar curves.

Partial Shape Similarity via Alignment of Multi-Metric Hamiltonian Spectra

Evaluating the similarity of non-rigid shapes with significant partiality is a fundamental task in numerous computer vision applications. Here, we propose a novel axiomatic method to match similar regions across shapes. Matching similar regions is formulated as the alignment of the spectra of operators closely related to the Laplace-Beltrami operator (LBO). The main novelty of the proposed approach is the consideration of differential operators defined on a manifold with multiple metrics. The choice of a metric relates to fundamental shape properties while considering the same manifold under different metrics can thus be viewed as analyzing the underlying manifold from different perspectives. Specifically, we examine the scale-invariant metric and the corresponding scale-invariant Laplace-Beltrami operator (SI-LBO) along with the regular metric and the regular LBO. We demonstrate that the scale-invariant metric emphasizes the locations of important semantic features in articulated shapes. A truncated spectrum of the SI-LBO consequently better captures locally curved regions and complements the global information encapsulated in the truncated spectrum of the regular LBO. We show that matching these dual spectra outperforms competing axiomatic frameworks when tested on standard benchmarks. We introduced a new dataset and compare the proposed method with the state-of-the-art learning based approach in a cross-database configuration. Specifically, we show that, when trained on one data set and tested on another, the proposed axiomatic approach which does not involve training, outperforms the deep learning alternative.

Garment Avatars: Realistic Cloth Driving using Pattern Registration

Virtual telepresence is the future of online communication. Clothing is an essential part of a person's identity and self-expression. Yet, ground truth data of registered clothes is currently unavailable in the required resolution and accuracy for training telepresence models for realistic cloth animation. Here, we propose an end-to-end pipeline for building drivable representations for clothing. The core of our approach is a multi-view patterned cloth tracking algorithm capable of capturing deformations with high accuracy. We further rely on the high-quality data produced by our tracking method to build a Garment Avatar: an expressive and fully-drivable geometry model for a piece of clothing. The resulting model can be animated using a sparse set of views and produces highly realistic reconstructions which are faithful to the driving signals. We demonstrate the efficacy of our pipeline on a realistic virtual telepresence application, where a garment is being reconstructed from two views, and a user can pick and swap garment design as they wish. In addition, we show a challenging scenario when driven exclusively with body pose, our drivable garment avatar is capable of producing realistic cloth geometry of significantly higher quality than the state-of-the-art.

Elastica Models for Color Image Regularization

One classical approach to regularize color is to tream them as two dimensional surfaces embedded in a five dimensional spatial-chromatic space. In this case, a natural regularization term arises as the image surface area. Choosing the chromatic coordinates as dominating over the spatial ones, the image spatial coordinates could be thought of as a paramterization of the image surface manifold in a three dimensional color space. Minimizing the area of the image manifold leads to the Beltrami flow or mean curvature flow of the image surface in the 3D color space, while minimizing the elastica of the image surface yields an additional interesting regularization. Recently, the authors proposed a color elastica model, which minimizes both the surface area and elastica of the image manifold. In this paper, we propose to modify the color elastica and introduce two new models for color image regularization. The revised measures are motivated by the relations between the color elastica model, Euler's elastica model and the total variation model for gray level images. Compared to our previous color elastica model, the new models are direct extensions of Euler's elastica model to color images. The proposed models are nonlinear and challenging to minimize. To overcome this difficulty, two operator-splitting methods are suggested. Specifically, nonlinearities are decoupled by introducing new vector- and matrix-valued variables. Then, the minimization problems are converted to solving initial value problems which are time-discretized by operator splitting. Each subproblem, after splitting either, has a closed-form solution or can be solved efficiently. The effectiveness and advantages of the proposed models are demonstrated by comprehensive experiments. The benefits of incorporating the elastica of the image surface as regularization terms compared to common alternatives are empirically validated.

Deep Signatures -- Learning Invariants of Planar Curves

We propose a learning paradigm for numerical approximation of differential invariants of planar curves. Deep neural-networks' (DNNs) universal approximation properties are utilized to estimate geometric measures. The proposed framework is shown to be a preferable alternative to axiomatic constructions. Specifically, we show that DNNs can learn to overcome instabilities and sampling artifacts and produce numerically-stable signatures for curves subject to a given group of transformations in the plane. We compare the proposed schemes to alternative state-of-the-art axiomatic constructions of group invariant arc-lengths and curvatures.

Depth Refinement for Improved Stereo Reconstruction

Depth estimation is a cornerstone of a vast number of applications requiring 3D assessment of the environment, such as robotics, augmented reality, and autonomous driving to name a few. One prominent technique for depth estimation is stereo matching which has several advantages: it is considered more accessible than other depth-sensing technologies, can produce dense depth estimates in real-time, and has benefited greatly from the advances of deep learning in recent years. However, current techniques for depth estimation from stereoscopic images still suffer from a built-in drawback. To reconstruct depth, a stereo matching algorithm first estimates the disparity map between the left and right images before applying a geometric triangulation. A simple analysis reveals that the depth error is quadratically proportional to the object's distance. Therefore, constant disparity errors are translated to large depth errors for objects far from the camera. To mitigate this quadratic relation, we propose a simple but effective method that uses a refinement network for depth estimation. We show analytical and empirical results suggesting that the proposed learning procedure reduces this quadratic relation. We evaluate the proposed refinement procedure on well-known benchmarks and datasets, like Sceneflow and KITTI datasets, and demonstrate significant improvements in the depth accuracy metric.

Unsupervised High-Fidelity Facial Texture Generation and Reconstruction

Many methods have been proposed over the years to tackle the task of facial 3D geometry and texture recovery from a single image. Such methods often fail to provide high-fidelity texture without relying on 3D facial scans during training. In contrast, the complementary task of 3D facial generation has not received as much attention. As opposed to the 2D texture domain, where GANs have proven to produce highly realistic facial images, the more challenging 3D geometry domain has not yet caught up to the same levels of realism and diversity. In this paper, we propose a novel unified pipeline for both tasks, generation of both geometry and texture, and recovery of high-fidelity texture. Our texture model is learned, in an unsupervised fashion, from natural images as opposed to scanned texture maps. To the best of our knowledge, this is the first such unified framework independent of scanned textures. Our novel training pipeline incorporates a pre-trained 2D facial generator coupled with a deep feature manipulation methodology. By applying precise 3DMM fitting, we can seamlessly integrate our modeled textures into synthetically generated background images forming a realistic composition of our textured model with background, hair, teeth, and body. This enables us to apply transfer learning from the domain of 2D image generation, thus, benefiting greatly from the impressive results obtained in this domain. We provide a comprehensive study on several recent methods comparing our model in generation and reconstruction tasks. As the extensive qualitative, as well as quantitative analysis, demonstrate, we achieve state-of-the-art results for both tasks.

Colored Point Cloud to Image Alignment

Recognition and segmentation of objects in images enjoy the wealth of large volume of well annotated data. At the other end, when dealing with the reconstruction of geometric structures of objects from images, there is a limited amount of accurate data available for supervised learning. One type of such geometric data with insufficient amount required for deep learning is real world accurate RGB-D images. The lack of accurate RGB-D datasets is one of the obstacles in the evolution of geometric scene reconstructions from images. One solution to creating such a dataset is to capture RGB images while simultaneously using an accurate depth scanning device that assigns a depth value to each pixel. A major challenge in acquiring such ground truth data is the accurate alignment between the RGB images and the measured depth and color profiles. We introduce a differential optimization method that aligns a colored point cloud to a given color image via iterative geometric and color matching. The proposed method enables the construction of RGB-D datasets for specific camera systems. In the suggested framework, the optimization minimizes the difference between the colors of the image pixels and the corresponding colors of the projected points to the camera plane. We assume that the colors produced by the geometric scanner camera and the color camera sensor are different and thus are characterized by different chromatic acquisition properties. We align the different color spaces while compensating for their corresponding color appearance. Under this setup, we find the transformation between the camera image and the point cloud colors by iterating between matching the relative location of the point cloud and matching colors. The successful alignments produced by the proposed method are demonstrated on both synthetic data with quantitative evaluation and real world scenes with qualitative results.

U-mesh: Human Correspondence Matching with Mesh Convolutional Networks

The proliferation of 3D scanning technology has driven a need for methods to interpret geometric data, particularly for human subjects. In this paper we propose an elegant fusion of regression (bottom-up) and generative (top-down) methods to fit a parametric template model to raw scan meshes. Our first major contribution is an intrinsic convolutional mesh U-net architecture that predicts pointwise correspondence to a template surface. Soft-correspondence is formulated as coordinates in a newly-constructed Cartesian space. Modeling correspondence as Euclidean proximity enables efficient optimization, both for network training and for the next step of the algorithm. Our second contribution is a generative optimization algorithm that uses the U-net correspondence predictions to guide a parametric Iterative Closest Point registration. By employing pre-trained human surface parametric models we maximally leverage domain-specific prior knowledge. The pairing of a mesh-convolutional network with generative model fitting enables us to predict correspondence for real human surface scans including occlusions, partialities, and varying genus (e.g. from self-contact). We evaluate the proposed method on the FAUST correspondence challenge where we achieve 20% (33%) improvement over state of the art methods for inter- (intra-) subject correspondence.